ray/rllib/agents/ddpg at 97d6509cf85232d0cb2be671daade7328eafc00a - ray

mirror of https://github.com/wassname/ray.git synced 2026-07-01 09:27:40 +08:00

Files

T

Sven Mika 7ec2223c84 [RLlib] DDPG PyTorch actor-model was missing sigmoid layer (#8188 )

Fix DDPG PyTorch (missing sigmoid layer (to squash action outputs) after deterministic action outputs).

2020-04-26 23:08:13 +02:00

2019-08-05 23:25:49 -07:00

2020-04-26 23:08:13 +02:00

__init__.py

2020-04-16 10:20:01 +02:00

apex.py

2020-03-14 12:05:04 -07:00

ddpg_tf_model.py

2020-04-16 10:20:01 +02:00

ddpg_tf_policy.py

2020-04-26 23:08:13 +02:00

ddpg_torch_model.py

2020-04-26 23:08:13 +02:00

ddpg_torch_policy.py

2020-04-26 23:08:13 +02:00

ddpg.py

2020-04-16 10:20:01 +02:00

noop_model.py

2020-04-16 10:20:01 +02:00

OBSOLETED_ddpg_policy.py

2020-04-16 10:20:01 +02:00

README.md

2019-08-05 23:25:49 -07:00

td3.py

2020-04-16 10:20:01 +02:00

Implementation of deep deterministic policy gradients (https://arxiv.org/abs/1509.02971), including an Ape-X variant.